Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 10:44:09 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update NRC

Browse Source
This commit is contained in:
Kovid Goyal 2015-10-22 10:22:32 +05:30
parent eb18b57463
commit 8dd12103d1
1 changed files with 18 additions and 48 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

66
recipes/nrc.nl.recipe
View File

@ -5,6 +5,7 @@ nrc.nl
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class Pagina12(BasicNewsRecipe):
title = 'NRC'
@ -21,56 +22,25 @@ class Pagina12(BasicNewsRecipe):
country = 'NL'
remove_empty_feeds = True
masthead_url = 'http://www.nrc.nl/nrc.nl/images/logo_nrc.png'
extra_css = """
body{font-family: Georgia,serif }
img{margin-bottom: 0.4em; display: block}
.bijschrift,.sectie{font-size: x-small}
.sectie{color: gray}
"""
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags = [
dict(name=['h1', 'figure']),
dict(attrs={'class':['intro', 'byline']}),
dict(attrs={'class':lambda x: x and 'article__content' in x}),
]
remove_attributes = ['style']
keep_only_tags = [dict(attrs={'class':'uitstekendekeus'})]
remove_tags = [
dict(name=['meta','base','link','object','embed'])
,dict(attrs={'class':['reclamespace','tags-and-sharing','sharing-is-caring']})
]
remove_attributes=['lang']
feeds = [
(u'Voor nieuws', u'http://www.nrc.nl/nieuws/categorie/nieuws/rss.php' )
,(u'Binnenland' , u'http://www.nrc.nl/nieuws/categorie/binnenland/rss.php' )
,(u'Buitenland' , u'http://www.nrc.nl/nieuws/categorie/buitenland/rss.php' )
,(u'Economie' , u'http://www.nrc.nl/nieuws/categorie/economie/rss.php' )
,(u'Cultuur' , u'http://www.nrc.nl/nieuws/categorie/cultuur/rss.php' )
,(u'Sport' , u'http://www.nrc.nl/nieuws/categorie/sport/rss.php' )
,(u'Wetenschap ', u'http://www.nrc.nl/nieuws/categorie/wetenschap-nieuws/rss.php')
]
feeds = ['http://www.nrc.nl/rss/']
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll('a'):
limg = item.find('img')
if item.string is not None:
str = item.string
item.replaceWith(str)
else:
if limg:
item.name = 'div'
atritems =['href','target','rel']
for atit in atritems:
if item.has_key(atit):
del item[atit]
else:
str = self.tag_to_string(item)
item.replaceWith(str)
for item in soup.findAll('img'):
if not item.has_key('alt'):
item['alt'] = 'image'
src = None
for meta in soup.findAll('meta', itemprop='image', content=True):
src = meta['content']
break
if src is not None:
div = soup.find('div', attrs={'class':lambda x: x and 'featured-img' in x})
if div is not None:
img = Tag(soup, 'img')
img['src'] = src
div.append(img)
return soup